×

zbMATH — the first resource for mathematics

Adaptive total variation image deblurring: a majorization-minimization approach. (English) Zbl 1178.94029
Summary: This paper presents a new approach to image deconvolution (deblurring), under total variation (TV) regularization, which is adaptive in the sense that it does not require the user to specify the value of the regularization parameter. We follow the Bayesian approach of integrating out this parameter, which is achieved by using an approximation of the partition function of the Bayesian prior interpretation of the TV regularizer. The resulting optimization problem is then attacked using a majorization-minimization algorithm. Although the resulting algorithm is of the iteratively reweighted least squares (IRLS) type, thus suffering of the infamous “singularity issue”, we show that this issue is in fact not problematic, as long as adequate initialization is used. Finally, we report experimental results showing that the proposed methodology achieves state-of-the-art performance, on par with TV-based methods with hand tuned regularization parameters, as well as with the best wavelet-based methods.

MSC:
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
Software:
ForWaRD; DT-CWT; RecPF
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Bertero, M.; Boccacci, P.: Introduction to inverse problems in imaging, (1998) · Zbl 0914.65060
[2] T. Chan, J. Shen, Image Processing and Analysis — Variational, PDE, Wavelet, and Stochastic Methods, SIAM, Philadelphia, PA, 2005. · Zbl 1095.68127
[3] Archer, G.; Titterington, D.: On some Bayesian/regularization methods for image restoration, IEEE transactions on image processing 4, No. 7, 989-995 (1995)
[4] S. Geman, C. Graffigne, Markov random field image models and their applications to computer vision, in: Proceedings of the International Congress of Mathematicians, 1987, pp. 1496 – 1517. · Zbl 0665.68067
[5] Chellappa, R.; Jain, A.: Markov random fields: theory and applications, (1993)
[6] Jeng, F.; Woods, J.: Compound Gauss – Markov random fields for image estimation, IEEE transactions on signal processing 39, 683-697 (March 1991)
[7] Li, S. Z.: Markov random field modelling in computer vision, (1995)
[8] Donoho, D.: Nonlinear solution of linear inverse problems by wavelet-vaguelette decompositions, Journal of applied and computational harmonic analysis 1, 100-115 (1995) · Zbl 0826.65117
[9] Banham, M.; Katsaggelos, A.: Spatially adaptive wavelet-based multiscale image restoration, IEEE transactions on image processing 5, 619-634 (1996)
[10] A. Jalobeanu, N. Kingsbury, J. Zerubia, Image deconvolution using hidden Markov tree modeling of complex wavelet packets, in: IEEE International Conference on Image Processing — ICIP’01, 2001.
[11] Figueiredo, M.; Nowak, R.: An EM algorithm for wavelet-based image restoration, IEEE transactions on image processing 12, No. 8, 906-916 (2003) · Zbl 1279.94015
[12] Bioucas-Dias, J.: Bayesian wavelet-based image deconvolution: a GEM algorithm exploiting a class of heavy-tailed priors, IEEE transactions on image processing 15, No. 4, 937-951 (2006)
[13] M. Figueiredo, R. Nowak, A bound optimization approach to wavelet-based image deconvolution, in: IEEE International Conference on Image Processing — ICIP’2005, Genoa, Italy, 2005.
[14] P. de Rivaz, N. Kingsbury, Bayesian image deconvolution and denoising using complex wavelets, in: Proceedings of the 2001 International Conference on Image Processing, vol. 2, 2001, pp. 273 – 276.
[15] L. Rudin, S. Osher, E. Fatemi, Nonlinear total variation based noise removal algorithms, Physica D (1992) 259 – 268. · Zbl 0780.49028
[16] J. Bioucas-Dias, M. Figueiredo, J.P. Oliveira, Total variation-based image deconvolution: a majorization – minimization approach, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. II, 2006, pp. 861 – 864.
[17] Chan, T.; Esedoglu, S.; Park, F.; Yip, A.: Recent developments in total variation image restoration, Handbook of mathematical models in computer vision (2005)
[18] Chan, T.; Wong, C.: Total variation blind deconvolution, IEEE transactions on image processing 7, 365-370 (1998)
[19] Chambolle, A.: An algorithm for total variation minimization and applications, Journal of mathematical imaging and vision 20, 89-97 (2004) · Zbl 1366.94048
[20] A. Chambolle, Total variation minimization and a class of binary MRF models, in: 5th International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, Springer Lecture Notes in Computer Science, vol. 3757, Springer, Berlin, 2005, pp. 136 – 152.
[21] Darbon, J.; Sigelle, M.: Image restoration with discrete constrained total variation (part I): fast and exact optimization, Journal of mathematical imaging and vision 26, 261-276 (2006)
[22] M. Figueiredo, J. Bioucas-Dias, J.P. Oliveira, R. Nowak, On total-variation denoising: a new majorization – minimization algorithm and an experimental comparison with wavalet denoising, in: IEEE International Conference on Image Processing — ICIP’2006, 2006.
[23] Vogel, C.; Oman, M.: Iterative method for total variation denoising, SIAM journal on scientific computing 17, 227-238 (1996) · Zbl 0847.65083
[24] Wang, Y.; Yang, J.; Yin, W.; Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction, SIAM journal on imaging sciences 1, 248-272 (2008) · Zbl 1187.68665
[25] Hunter, D.; Lange, K.: A tutorial on MM algorithms, The American statistician 58, 30-37 (2004)
[26] Dempster, A.; Laird, N.; Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm, Journal of the royal statistical society (B) 39, 1-38 (1977) · Zbl 0364.62022
[27] Huber, P.: Robust statistics, (1981) · Zbl 0536.62025
[28] J. Bioucas-Dias, M. Figueiredo, J.P. Oliveira, Adaptive Bayesian/total-variation image deconvolution: a majorization – minimization approach, in: European Signal Processing Conference — EUSIPCO’2006, 2006. · Zbl 1178.94029
[29] Wu, C.: On the convergence properties of the EM algorithm, The annals of statistics 11, 95-103 (1983) · Zbl 0517.62035
[30] Nocedal, J.; Wright, S.: Numerical optimization, (1999) · Zbl 0930.65067
[31] Figueiredo, M.; Bioucas-Dias, J.; Nowak, R.: Majorization – minimization algorithms for wavelet-based image restoration, IEEE transactions on image processing 12, 2980-2991 (2007)
[32] Vogel, C.: Computational methods for inverse problems, (2002) · Zbl 1008.65103
[33] Galatsanos, N.; Katsaggelos, A.: Methods for choosing the regularization parameter and estimating the noise variance in image restoration and their relation, IEEE transactions on image processing 1, 322-336 (1992)
[34] N. Galatsanos, V. Mesarovic, R. Molina, J. Mateos, A. Katsaggelos, Hyper-parameter estimation using gamma hyper-priors in image restoration from partially-known blurs, Optical Engineering 41 (2002) 1845 – 1854.
[35] Molina, R.; Katsaggelos, A.; Mateos, J.: Bayesian and regularization methods for hyperparameter estimation in image restoration, IEEE transactions on image processing 8, No. 2, 231-246 (1999) · Zbl 1098.94509
[36] Mohammad-Djafari, A.: A full Bayesian approach for inverse problems, Maximum entropy and Bayesian methods (1996) · Zbl 0886.62031
[37] Deng, G.: Iterative learning algorithms for linear Gaussian observation models, IEEE transactions on signal processing 52, 2286-2297 (2004) · Zbl 1369.68279
[38] Bernardo, J.; Smith, A.: Bayesian theory, (1994) · Zbl 0796.62002
[39] Besag, J.: On the statistical analysis of dirty pictures, Journal of the royal statistical society B 48, 259-302 (1986) · Zbl 0609.62150
[40] Jain, A. K.: Fundamentals of digital image processing, (1989) · Zbl 0744.68134
[41] M. Mignotte, An adaptive segmentation-based regularization term for image restoration, in: IEEE International Conference on Image Processing, 2005.
[42] Neelamani, R.; Choi, H.; Baraniuk, R.: Forward: Fourier-wavelet regularized deconvolution for ill-conditioned systems, IEEE transactions on signal processing 52, No. 2, 418-433 (2004) · Zbl 1369.94238
[43] Y. Lin, B. Wohlberg, Application of the UPRE method to optimal parameter selection for large scale regularization problems, in: IEEE Southwest Symposium on Image Analysis and Interpretation, 2008, pp. 89 – 92.
[44] H. Liao, F. Li, M. Ng, Generalized cross-validation for total variation image restoration, Technical Report 08-11, Institute for Computational Mathematics, Hong Kong Baptist University, 2008. Available at \langle http://www.math.hkbu.edu.hk/ICM/pdf/08-11.pdf\rangle .
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.